Metraipolis › archive › dc_93089592cfbc

ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering — arXiv:2609.36392

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.36392
License (as archived): CC0-1.0
Archived: 2026-10-07T16:22:34.767Z
SHA-256 of the archived text: 5e3cf465fad0ea50f2bdeaf56cde0eeb7c2fe40bdea68edab7d3998576c823a5
Stable URL of this page: https://metraipolis.com/documento/dc_93089592cfbc

How to cite

ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering — arXiv:2609.36392 — arXiv (en), https://arxiv.org/abs/2609.36392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_93089592cfbc (Metraipolis archive dc_93089592cfbc, sha256 5e3cf465fad0ea50f2bdeaf56cde0eeb7c2fe40bdea68edab7d3998576c823a5)

BibTeX

@misc{dc93089592cfbc,
  title = {ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering — arXiv:2609.36392},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36392},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_93089592cfbc; sha256 5e3cf465fad0ea50f2bdeaf56cde0eeb7c2fe40bdea68edab7d3998576c823a5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In diseases where clinical guidelines are incomplete, contested, or mutually contradictory, knowledge completeness and dynamic conflict-aware synthesis are two safety-critical properties that standard Retrieval-Augmented Generation systems do not provide. Therefore, we present \sysname, an adaptive retrieval calibration clinical question-answering agent for ME/CFS, a disease where diagnostic frameworks coexist and major guidelines actively contradict each other on treatment. ARCagent contributes three components. First, a 1,706-chunk, 10-source knowledge base with a structured inter-guideline conflict registry spanning all active ME/CFS diagnostic frameworks. Second, a conflict-aware retrieval calibration pipeline that re-ranks retrieved evidence using query-specific focus and conflict signals. Third, a benchmark scored by LLM-as-Judge, avoiding systematic underestimation averaging 10.1 percentage points caused by keyword matching. ARCagent achieves 95.3%, outperforming all base LLMs. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.36392 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.496Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).